{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T19:59:32Z","timestamp":1783627172158,"version":"3.55.0"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100011535","name":"Missouri University of Science and Technology Intelligent Systems Center","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100011535","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Mary K. Finley Missouri Endowment"},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"Lifelong Learning Machines Program from the DARPA\/Microsystems Technology Office","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006754","name":"Army Research Laboratory","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Cooperative Agreement","award":["W911NF-18-2-0260"],"award-info":[{"award-number":["W911NF-18-2-0260"]}]},{"name":"Higher Committee for Educational Development"},{"name":"Basra Oil Company (BOC), Iraq"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2020,4]]},"DOI":"10.1109\/tnnls.2019.2919338","type":"journal-article","created":{"date-parts":[[2019,6,20]],"date-time":"2019-06-20T20:45:10Z","timestamp":1561063510000},"page":"1155-1169","source":"Crossref","is-referenced-by-count":37,"title":["An Improved <i>N<\/i>-Step Value Gradient Learning Adaptive Dynamic Programming Algorithm for Online Learning"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5200-7587","authenticated-orcid":false,"given":"Seaar","family":"Al-Dabooni","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9726-9051","authenticated-orcid":false,"given":"Donald C.","family":"Wunsch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1002\/9781118453988.ch3"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2015.2505327"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.02.005"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2015.06.001"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2281663"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.1989.4790360"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2654324"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1109\/TSMCB.2012.2216523","article-title":"Finite-approximation-error-based optimal control approach for discrete-time nonlinear systems","volume":"43","author":"liu","year":"2013","journal-title":"IEEE Trans Cybern"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.926614"},{"key":"ref60","article-title":"The local optimality of reinforcement learning by value gradients, and its relationship to policy gradient learning","author":"fairbank","year":"2011","journal-title":"arXiv 1101 0428"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2000396"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2283574"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/72.701173"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2357896"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta:20050341"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2616644"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2009.2025508"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1002\/9781118025604"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2009.933854"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11768-011-1005-3"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.04.014"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIA.2003.809438"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2329942"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727679"},{"key":"ref23","first-page":"248","article-title":"A comparison of dual heuristic programming (DHP) and neural network based stochastic optimization approach on collective robotic search problem","author":"zhang","year":"2003","journal-title":"Proc Int Joint Conf Neural Netw (IJCNN)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2014.2301770"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1109\/TNNLS.2013.2292704","article-title":"Reinforcement learning output feedback NN control using deterministic learning technique","volume":"25","author":"xu","year":"2014","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref50","first-page":"1","article-title":"True online temporal-difference learning","volume":"145","author":"seijen","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015961"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(90)90005-6"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1086\/209106"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3182\/20060517-3-FR-2903.00330"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/S0377-2217(98)00051-4"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/5.58337"},{"key":"ref54","doi-asserted-by":"crossref","first-page":"2038","DOI":"10.1109\/TNNLS.2013.2271454","article-title":"Goal representation heuristic dynamic programming on maze navigation","volume":"24","author":"ni","year":"2013","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2875870"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2919614"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2490698"},{"key":"ref11","author":"bellman","year":"1957","journal-title":"Dynamic Programming"},{"key":"ref40","first-page":"1","article-title":"True Online Temporal-Difference Learning","volume":"145","author":"van seijen","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/72.623201"},{"key":"ref13","article-title":"Approximate dynamic programming for real-time control and neural modeling","author":"werbos","year":"1992","journal-title":"Handbook of Intelligent Control Neural Fuzzy and Adaptive Approaches"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2009.932261"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.924141"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2009.2027233"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/72.914523"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2424971"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2011.05.031"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2585520"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2006.08.010"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2247627"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"1133","DOI":"10.1109\/TNN.2011.2147797","article-title":"Adaptive learning and control for MIMO system based on adaptive dynamic programming","volume":"22","author":"fu","year":"2011","journal-title":"IEEE Trans Neural Netw"},{"key":"ref8","author":"lewis","year":"2013","journal-title":"Reinforcement Learning and Approximate Dynamic Programming for Feedback Control"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/9780470544785"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114726"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2013.2284545"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1002\/9781118122631"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966204"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2271778"},{"key":"ref42","first-page":"692","article-title":"True online TD(\n$\\lambda$\n)","author":"seijen","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref41","first-page":"1","article-title":"An emphatic approach to the problem of off-policy temporal-difference learning","volume":"73","author":"sutton","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref44","author":"lewis","year":"2013","journal-title":"Reinforcement Learning and Approximate Dynamic Programming for Feedback Control"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252791"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/5962385\/9056859\/8742790-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9056859\/08742790.pdf?arnumber=8742790","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:19:34Z","timestamp":1651079974000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8742790\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4]]},"references-count":65,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2019.2919338","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,4]]}}}